UniCourt AI Integration
UniCourt AI agents from Bonfire Terminal help you work with legal court records using your UniCourt context and credentials. Running locally on your machine, they summarize case filings, track dockets, and organize litigation data from Slack or Telegram.
What Bonfire can do in UniCourt
Real actions from the UniCourt API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Get Attorney By Id | Case Docket API | GET /attorney/{attorneyId} |
| Get Attorney Associated Parties | Case Docket API | GET /attorney/{attorneyId}/associatedParties |
| Get Billing Usage By Billing Cycle | Usage API | GET /billingCycleUsage/{billingCycle} |
| Get Billing Cycles | Usage API | GET /billingCycles |
| Get Callbacks | Callback API | GET /callbacks |
| Get Case Documents | Case Documents API | GET /case/{caseId}/documents |
| Get Case Count Analytics By Area Of Law | Case Analytics API | GET /caseCountAnalyticsByAreaOfLaw |
| Get Case Count Analytics By Case Class | Case Analytics API | GET /caseCountAnalyticsByCaseClass |
UniCourt agents in action
On your machine, not a SaaS
Bonfire Terminal
- Your keys & data stay on your device
- Perpetual license — no per-seat SaaS fee
- Any connected model — Claude, GPT, Gemini or Grok
- Offline Llama for local, private reasoning
- Driven from chat you already use
Cloud AI middleman
- Keys & data pass through a third-party server
- Recurring subscription, usage caps
- Model locked to the vendor
- Yet another dashboard to log into
UniCourt — questions
Can Bonfire automate UniCourt?
Yes. Bonfire runs on your machine, holds your UniCourt credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the UniCourt API to run the actions you ask for in chat.
Does my UniCourt data go to the cloud?
Bonfire runs on your desktop and keeps your keys local — it isn't a SaaS holding your data. Only the specific request you approve is sent to your chosen AI model.
Which AI models can I use?
Any connected model — Claude, GPT, Gemini or Grok. A fully offline Llama model runs locally for private reasoning but can't reach live APIs.